Heuristic method of classification

• US 7,499,891 B2
• Filed: 04/13/2007
• Issued: 03/03/2009
• Est. Priority Date: 06/19/2000
• Status: Expired due to Fees

• Current Assignee: Vermillion, Inc.
• Original Assignee: Correlogic Systems, Inc. (Aspira Women's Health, Inc.)
• Inventors: Hitt, Ben
• Primary Examiner(s): Hirl; Joseph P
• Application Number:
  US11/735,028
• Publication Number:
  US 20070185824A1
• Time in Patent Office: 690 Days
• Field of Search: 706/12, 706/14, 706/900, 600/316
• US Class Current: 706/12
• CPC Class Codes: G06F 18/21 Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
• CPC Class Codes: G06F 18/211 Selection of the most significant subset of features
• CPC Class Codes: G06F 18/2433 Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: Y10S 706/90 Fuzzy logic
• CPC Class Codes: Y10S 706/932 Mathematics, science, or engineering

Abstract

The invention concerns heuristic algorithms for the classification of Objects. A first learning algorithm comprises a genetic algorithm that is used to abstract a data stream associated with each Object and a pattern recognition algorithm that is used to classify the Objects and measure the fitness of the chromosomes of the genetic algorithm. The learning algorithm is applied to a training data set. The learning algorithm generates a classifying algorithm, which is used to classify or categorize unknown Objects. The invention is useful in the areas of classifying texts and medical samples, predicting the behavior of one financial market based on price changes in others and in monitoring the state of complex process facilities to detect impending failures.

Claims

1. A computer implemented method of creating a classifying pattern for biological samples using a plurality of data strings, comprising:

selecting a set of data elements from each data string using a learning algorithm, each data string being associated with one of a plurality of biological samples to be classified, each of the plurality of biological samples being of a first state or a second state;

classifying the set of data elements using a pattern recognition algorithm; and

repeating the selecting and the classifying with a different set of data elements selected from each data string until a classifying pattern is created that is acceptable to classify biological samples as being of a first state or a second state.

2. The method of claim 1, wherein the learning algorithm is an evolutionary algorithm.

3. The method of claim 1, wherein the learning algorithm is a genetic algorithm.

4. The method of claim 1, wherein the data strings are of a type are selected from the group consisting of:

(a) mass spectrometry data, (b) hybridization data, (c) gene expression data, and (d) microarray data.

5. The method of claim 1, wherein the pattern recognition algorithm is an adaptive pattern recognition algorithm.

6. A computer readable medium having stored thereon data representing a classifying pattern constructed using the method of claim 1.

7. A classifying pattern constructed using the method of claim 1.

8. A computer implemented method of creating a classifying pattern for objects using a plurality of data strings, each data string associated with one of a plurality of objects to be classified, comprising:

selecting a set of data elements from each data string using a learning algorithm, the set of data elements being less than all of the data elements of each data string;

classifying the set of data elements using a pattern recognition algorithm; and

repeating the selecting and the classifying with a different set of data elements selected from each data string until a classifying pattern is created that is acceptable to classify the objects.

9. The method of claim 8, wherein the learning algorithm is an evolutionary algorithm.

10. The method of claim 8, wherein the learning algorithm is a genetic algorithm.

11. The method of claim 8, wherein the data strings are of a type are selected from the group consisting of:

(a) mass spectrometry data, (b) hybridization data, (c) gene expression data, (d) microarray data, (e) financial data, (f) stock market data, (g) text, (h) currency exchange rates, and (i) processing plant control status values.

12. The method of claim 8, wherein the pattern recognition algorithm is an adaptive pattern recognition algorithm.

13. The method of claim 12, wherein the pattern recognition algorithm creates a cluster map having a plurality of clusters associated with the set of data points.

14. The method of claim 13, wherein acceptability of a grouping as a classifying pattern to classify the objects is based on the homogeneity of the clusters in the cluster map.

15. The method of claim 13, wherein a grouping is acceptable as a classifying pattern to classify the objects if a homogeneity of the cluster map is within a predetermined tolerance.

16. The method of claim 13, wherein the cluster map is created by

calculating a vector for each set of data points;

and

mapping the vectors into a vector space.

17. The method of claim 16, further comprising:

determining if a distance of at least one of the vectors from a closest preexisting centroid is within a predetermined threshold distance.

18. A computer readable medium having stored thereon data representing a classifying pattern constructed using the method of claim 8.

19. A classifying pattern constructed using the method of claim 8.

20. The method of claim 8, wherein the objects are known to be of a first state or a second state and the classifying pattern classifies objects by state.